Project effect estimation system and method based on historical approval data
By modularly processing and feature analysis of historical approval data and optimizing the selection of approval nodes, the problems of backlog of approval materials and difference in reliability in the approval process are solved, and efficient parallelization and systematic health of the approval process are achieved.
Patent Information
- Application Number
- CN202411075964.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-07
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2044-08-07
AI Technical Summary
In the project approval process, due to the difference in material recognition reliability of different approving parties and the uneven backlog of approval materials, the approval progress is delayed and the difficulty of process optimization is increased. A project effectiveness estimate system based on historical approval data is needed to optimize the approval process. .
By modularly segmenting historical approval materials, screening and quantifying feature parameters, building multi-dimensional feature vectors, clustering approval nodes, calculating permission proportional factors and approval effectiveness evaluation values, optimizing approval node selection and process arrangement, ensuring parallel processing of approval materials and process efficiency.
The parallel allocation of approval nodes for approval materials has been realized, the efficiency and smoothness of the approval process has been improved, the authority and persuasiveness of the approval results have been ensured, and the health and sustainability of the system has been ensured through periodic efficiency assessment.
Smart Images

Figure CN119090417A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of data analysis, and in particular to a system and method for estimating project effectiveness based on historical approval data. Background Art
[0002] With the continuous development of the economy, the complexity of projects in various fields is constantly increasing, and the project approval process is becoming more and more complicated. In today's project approval process, most of the approval materials are submitted to the established approvers according to the project type and process. Since different approvers have different focuses on the approval materials, there are differences in the credibility of the same approval materials. Therefore, when submitting the approval materials, the same approval materials will only be approved by some approvers, resulting in delayed approval progress. When a large number of projects are approved at the same time, there are different backlogs of materials from different approvers, resulting in how to reasonably optimize the approval process when selecting the approval node, which is particularly critical in the overall process of the project.
[0003] Therefore, there is a need for a project effectiveness estimation system and method based on historical approval data, which can estimate the project approval effectiveness of the approver and allocate approval nodes to the approval materials in parallel. Summary of the invention
[0004] The purpose of the present invention is to provide a system and method for estimating project effectiveness based on historical approval data to solve the problems raised in the above-mentioned background technology.
[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:
[0006] A project effectiveness estimation method based on historical approval data includes the following analysis steps:
[0007] Step S100: Acquire historical project approval materials, divide each historical project approval material into modules according to the content section, screen and quantify the characteristic parameters of the material modules, and construct a multi-dimensional characteristic vector of each material module;
[0008] Step S200: clustering approval nodes according to the multi-dimensional feature vectors of each material module and the final approval node to obtain the center point of each approval node cluster;
[0009] Step S300: Obtain the approval materials of the current project, use the method in step S100 to perform modular segmentation and multi-dimensional feature vector construction on the approval materials, and determine the approval priority of each material module;
[0010] Step S400: Calculate and analyze the authority ratio factors of each material module of each approval node and the current project approval material;
[0011] Step S500: Analyze the approval node selection results of each material module according to the authority ratio factor data and the remaining approval time of the material module to be approved at each approval node, and calculate and analyze the comprehensive approval effectiveness evaluation value of the current project approval material;
[0012] Step S600: setting an evaluation cycle and calculating and analyzing the comprehensive approval efficiency of each approval node within the evaluation cycle, and performing efficiency evaluation on each approval node.
[0013] In the above technical solution, step S100 includes the following contents:
[0014] Obtain all approval materials in historical projects, divide the approval materials of each historical project into different material modules according to the project type and approval material content section, and filter the characteristic parameters of each material module; among which, the material module characteristic parameters refer to the parameters with distinguishing characteristics between each material module;
[0015] Further, the characteristic parameters of each material module are quantified and assigned values, each type of type parameter is assigned a different reference value, and then a multi-dimensional characteristic vector is constructed according to the quantified characteristic parameters of each material module;
[0016] In the above technical solution, step S200 includes the following contents:
[0017] Obtain the final approval nodes of each material module of the historical project approval materials, cluster the material modules with the same approval nodes according to the corresponding multi-dimensional feature vectors, and obtain the center points of each approval node cluster;
[0018] For any approval node, according to the formula: in, is the equivalent multidimensional feature vector of the center point of the current approval node cluster, i is the number of the historical project material module approved by the current approval node, N is the number of historical project material modules approved by the current approval node, is the multidimensional feature vector of material module i;
[0019] In the above technical solution, determining the approval priority of each material module in step S300 includes the following contents:
[0020] By analyzing the order requirements of each material module in the project approval process, the approval priority of each material module is set; among them, if material module a is higher than material module b in the approval process, the approval priority of material module a is set higher than that of material module b; for material modules belonging to different projects, if the waiting approval time of material module a is longer than that of material module b, the approval priority of material module a is set higher than that of material module b; by sorting and comparing the priorities of material modules, the modular parallel approval process of project approval materials is carried out in an orderly manner, ensuring that the system reasonably and stably allocates approval nodes when a large number of approval materials are accepted;
[0021] In the above technical solution, step S400 includes the following contents:
[0022] Get the multi-dimensional feature vector of each material module in the current project approval material, calculate the authority distance between each approval node and each material module of the current project approval material, select any material module m and approval node n, according to the formula:
[0023]
[0024] Among them, D m,n is the authority distance between approval node n and material module m, p is the parameter number in the multidimensional feature vector of each material module, n p is the number of parameters in the multidimensional feature vector of each material module, is the parameter value of the characteristic parameter p in the multidimensional characteristic vector of material module m, is the parameter value of the characteristic parameter p in the equivalent multidimensional characteristic vector of the center point of the approval node cluster n;
[0025] Further calculate the authority ratio factor between material module m and approval node n according to the formula:
[0026]
[0027] Among them, F m,n is the authority ratio factor between material module m and approval node n, D m,n is the authority distance between approval node n and material module m, d is the approval node number, n d is the number of approval nodes, D m,d is the authority distance between material module m and approval node d;
[0028] In the above technical solution, step S500 includes the following contents:
[0029] Obtain the priority data of each material module, and select the approval node for each material module in descending order of priority; for material module m, calculate the approval effectiveness evaluation value of approval node n for the current material module m, according to the formula:
[0030]
[0031] Among them, E m,n is the evaluation value of the approval effectiveness of the approval node n on the current material module m, F m,n is the authority ratio factor between material module m and approval node n, i is the number of the material module to be approved assigned by approval node n, and n m The number of material modules to be approved assigned to approval node n, t i The remaining approval time of module i of the material to be approved at approval node n;
[0032] The approval effectiveness evaluation values of each approval node for material module m are sorted from large to small, and the approval node with the largest approval effectiveness evaluation value is selected as the approval node selection result of material module m; the authority distance between each material module and each approval node in the approval material is analyzed through a clustering algorithm, and the remaining approval time of the material module is introduced to comprehensively consider the authority ratio factor of each approval node when allocating the material module, so as to avoid case backlogs when allocating approval nodes, improve the efficiency of the approval process, and ensure the persuasiveness and feasibility of the allocation of approval nodes;
[0033] Set the authority ratio factor threshold F0 to make a threshold judgment on the authority ratio factor of the selected approval node for the current material module;
[0034] When the authority ratio factor of the selected approval node for the current material module is greater than or equal to F0, it is determined that the current material module only needs the selected approval node for approval, and the selected approval node is used as the approval node selection result of the current material module, and the approval effectiveness evaluation value of the selected approval node for the current material module is recorded;
[0035] When the authority ratio factor of the selected approval node for the current material module is less than F0, the approval node is selected for the current material module again, and the authority ratio factors of the twice selected approval nodes for the current material module are added together to perform the threshold judgment again, until the sum of the authority ratio factors of all the selected approval nodes is greater than or equal to F0, then all the approval nodes that need to be selected for the current material module are determined to be jointly approved, and all the selected approval nodes are used as the approval node selection results of the current material module, and the approval effectiveness evaluation values of all the selected approval nodes for the current material module are recorded;
[0036] By setting the authority ratio factor threshold and making threshold judgments, each material module can obtain sufficient approval in the approval process to ensure that the approval results obtained by the approval materials at different approval nodes are fully authoritative and persuasive. Through cross-node joint approval, the inherent approval authority recognition restrictions are broken, the approval channels are expanded, and the overall efficiency of the approval process is improved;
[0037] Calculate the comprehensive approval effectiveness evaluation value of all material modules in the current approval material according to the formula:
[0038]
[0039] Among them, E doc is the comprehensive approval effectiveness evaluation value of all material modules in the current approval material, j is the material module number of the current approval material, M doc The number of material modules divided for the current approval material, E j is the approval effectiveness evaluation value of material module j in the current approval material, n j is the number of nodes in the result of selecting the approval node of material module j in the current approval material; if material module j is determined to be jointly approved, then E j The value is the sum of the approval effectiveness evaluation values of all selected approval nodes for the current material module; the overall comprehensive approval effectiveness evaluation value of the approval materials is calculated and analyzed, providing a standardized approval effectiveness estimation and quantification method for the approval materials when they enter the approval process, thus achieving further optimization of the approval process;
[0040] In the above technical solution, step S600 includes the following contents:
[0041] Set the evaluation cycle of the approval node, obtain the authority ratio factor of all material modules approved by each approval node within the cycle and the current approval node; for any approval node n, calculate the comprehensive approval efficiency within the evaluation cycle according to the formula:
[0042]
[0043] Among them, E n is the comprehensive approval efficiency of approval node n in the evaluation cycle, k is the material module number of approval node n in the evaluation cycle, M n is the number of material modules approved by approval node n within the evaluation cycle, T k is the time taken for approval of material module k, F k,n is the authority ratio factor between material module k and approval node n;
[0044] By periodically conducting comprehensive approval efficiency assessments on approval nodes, we can ensure the healthy operation of each approval node in the approval system, ensure the adaptability and iterativeness of the approval process for project approval materials submission, and ensure the sustainable use of the approval system as a whole;
[0045] A specified number of approval nodes are selected from small to large based on the comprehensive approval efficiency, and the comprehensive approval efficiency of the selected approval nodes is fed back to the approval node supervisor to optimize the approval efficiency.
[0046] A project effectiveness estimation system based on historical approval data using the project effectiveness estimation method based on historical approval data described in the above technical solution, the system includes a historical data processing module, an approval material processing unit, and an approval evaluation module;
[0047] The historical data processing module is used to divide the historical project data into material modules, construct a multidimensional feature vector through feature parameter screening and quantification, and then obtain the cluster center of each approval node through a clustering algorithm; the approval material processing unit processes the approval materials according to the approval material processing method in the historical data processing module and analyzes the approval priority of each material module, calculates the approval effectiveness evaluation value of each material module of the approval material assigned to an approval node, and then selects the approval node of each material module; the approval evaluation module is used to analyze the comprehensive approval effectiveness evaluation value of the approval materials and the comprehensive approval efficiency of each approval node within the evaluation cycle;
[0048] In the above technical solution, the historical data processing module includes an approval material segmentation unit, a feature parameter quantification unit, and an approval node clustering unit;
[0049] The approval material segmentation unit segments the historical approval materials into material modules according to the project type and the approval material content section; the characteristic parameter quantification unit selects the characteristic parameters of each material module, assigns values to different characteristic parameters, and converts the type parameters into numerical parameters to construct a multidimensional characteristic vector; the approval node clustering unit performs cluster analysis according to the multidimensional characteristic vectors of the material modules approved by the approval nodes to obtain the cluster center of each approval node;
[0050] In the above technical solution, the approval evaluation module includes a comprehensive approval effectiveness evaluation unit and a comprehensive approval efficiency evaluation unit;
[0051] The comprehensive approval effectiveness evaluation unit is used to calculate and analyze the comprehensive approval effectiveness evaluation value of each approval material; the comprehensive approval efficiency evaluation unit is used to calculate and analyze the comprehensive approval efficiency of each approval node within the approval node evaluation cycle, select a specified number of approval nodes from small to large, and provide feedback to remind the approval node supervisor to optimize the approval efficiency.
[0052] Compared with the prior art, the beneficial effects achieved by the present invention are:
[0053] The present invention aims to realize parallel approval node allocation and process optimization of approval materials by dividing the approval materials into modules and conducting quantitative analysis, calculating the authority factors and approval effectiveness between the material modules and each approval node; by calculating the authority ratio factors between the material modules and each approval node, analyzing the credibility of each material module when selecting different approval nodes, setting the authority ratio factors, and determining whether each material module selects a single node for approval or multiple nodes for joint approval according to the approval effectiveness, providing more approval paths for the approval materials while ensuring that the selection results of various approval nodes are fully persuasive and authoritative; when selecting the approval nodes, the remaining approval time of the material modules to be approved at each approval node is introduced to calculate the approval effectiveness evaluation value, avoiding the overall delay of the approval process due to the backlog of project approval materials with similar characteristics at each approval node, ensuring the smoothness of the approval channel under the high concurrency scenario of the approval materials, and improving the overall efficiency of the approval system; in addition, the present invention also provides a periodic comprehensive approval efficiency evaluation method for approval nodes, which ensures the health and sustainable use of the approval process system by periodically evaluating the comprehensive approval efficiency of approval nodes and performing optimization feedback. BRIEF DESCRIPTION OF THE DRAWINGS
[0054] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:
[0055] Figure 1 It is a flow chart of a project effectiveness estimation method based on historical approval data of the present invention;
[0056] Figure 2 The invention discloses an organizational structure chart of a project effectiveness prediction system based on historical approval data. DETAILED DESCRIPTION
[0057] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0058] See also Figure 1-Figure 2 , the present invention provides a technical solution:
[0059] like Figure 1 As shown, the present invention provides a project effectiveness estimation method based on historical approval data, including the following analysis steps:
[0060] Step S100: Acquire historical project approval materials, divide each historical project approval material into modules according to the content section, screen and quantify the characteristic parameters of the material modules, and construct a multi-dimensional characteristic vector of each material module;
[0061] Step S200: clustering approval nodes according to the multi-dimensional feature vectors of each material module and the final approval node to obtain the center point of each approval node cluster;
[0062] Step S300: Obtain the approval materials of the current project, use the method in step S100 to perform modular segmentation and multi-dimensional feature vector construction on the approval materials, and determine the approval priority of each material module;
[0063] Step S400: Calculate and analyze the authority ratio factors of each material module of each approval node and the current project approval material;
[0064] Step S500: Analyze the approval node selection results of each material module according to the authority ratio factor data and the remaining approval time of the material module to be approved at each approval node, and calculate and analyze the comprehensive approval effectiveness evaluation value of the current project approval material;
[0065] Step S600: setting an evaluation cycle and calculating and analyzing the comprehensive approval efficiency of each approval node within the evaluation cycle, and performing efficiency evaluation on each approval node.
[0066] Step S100 includes the following contents:
[0067] Obtain all approval materials in historical projects, divide the approval materials of each historical project into different material modules according to the project type and approval material content section, and filter the characteristic parameters of each material module; among which, the material module characteristic parameters refer to the parameters with distinguishing characteristics between each material module;
[0068] Further, the characteristic parameters of each material module are quantified and assigned values, each type of type parameter is assigned a different reference value, and then a multi-dimensional characteristic vector is constructed according to the quantified characteristic parameters of each material module;
[0069] In specific implementation, the material module feature parameter screening can select project type, content section, investment type, investment benefit, project scale, etc.; when assigning feature parameter types, analyze the probability of material modules of each feature parameter type selecting the same approval node, and assign values to feature parameter types with higher probabilities closer to each other, to ensure that the feature clustering is tighter when calculating the cluster center points of each approval node, and reduce the possibility of misjudgment when selecting the material module approval node due to the close distance between the approval node cluster centers;
[0070] Step S200 includes the following contents:
[0071] Obtain the final approval nodes of each material module of the historical project approval materials, cluster the material modules with the same approval nodes according to the corresponding multi-dimensional feature vectors, and obtain the center points of each approval node cluster;
[0072] For any approval node, according to the formula: in, is the equivalent multidimensional feature vector of the center point of the current approval node cluster, i is the number of the historical project material module approved by the current approval node, N is the number of historical project material modules approved by the current approval node, is the multi-dimensional feature vector of material module i.
[0073] Determining the approval priority of each material module in step S300 includes the following:
[0074] By analyzing the order requirements of each material module in the project approval process, the approval priority of each material module is set; among them, if material module a is earlier than material module b in the approval process, the approval priority of material module a is set higher than that of material module b; for material modules belonging to different projects, if the waiting approval time of material module a is longer than that of material module b, the approval priority of material module a is set higher than that of material module b.
[0075] Step S400 includes the following contents:
[0076] Get the multi-dimensional feature vector of each material module in the current project approval material, calculate the authority distance between each approval node and each material module of the current project approval material, select any material module m and approval node n, according to the formula:
[0077]
[0078] Among them, D m,n is the authority distance between approval node n and material module m, p is the parameter number in the multidimensional feature vector of each material module, n p is the number of parameters in the multidimensional feature vector of each material module, is the parameter value of the characteristic parameter p in the multidimensional characteristic vector of material module m, is the parameter value of the characteristic parameter p in the equivalent multidimensional characteristic vector of the center point of the approval node cluster n;
[0079] Further calculate the authority ratio factor between material module m and approval node n according to the formula:
[0080]
[0081] Among them, F m,n is the authority ratio factor between material module m and approval node n, D m,nis the authority distance between approval node n and material module m, d is the approval node number, n d is the number of approval nodes, D m,d is the authority distance between material module m and approval node d;
[0082] Step S500 includes the following contents:
[0083] Obtain the priority data of each material module, and select the approval node for each material module in descending order of priority; for material module m, calculate the approval effectiveness evaluation value of approval node n for the current material module m, according to the formula:
[0084]
[0085] Among them, E m,n is the evaluation value of the approval effectiveness of the approval node n on the current material module m, F m,n is the authority ratio factor between material module m and approval node n, i is the number of the material module to be approved assigned by approval node n, and n m The number of material modules to be approved assigned to approval node n, t i The remaining approval time of module i of the material to be approved at approval node n;
[0086] In the specific implementation, considering that the more the number of pending approval materials is, the longer the remaining approval time is, the longer the current material module needs to wait for approval, and the more obvious the delay effect on the overall approval process of the project, the remaining approval time of the pending approval materials module is introduced as an approval effectiveness evaluation parameter;
[0087] Sort the approval effectiveness evaluation values of each approval node for material module m from large to small, and select the approval node with the largest approval effectiveness evaluation value as the approval node selection result for material module m;
[0088] Set the authority ratio factor threshold F0 to make a threshold judgment on the authority ratio factor of the selected approval node for the current material module;
[0089] When the authority ratio factor of the selected approval node for the current material module is greater than or equal to F0, it is determined that the current material module only needs the selected approval node for approval, and the selected approval node is used as the approval node selection result of the current material module, and the approval effectiveness evaluation value of the selected approval node for the current material module is recorded;
[0090] When the authority ratio factor of the selected approval node for the current material module is less than F0, the approval node is selected for the current material module again, and the authority ratio factors of the twice selected approval nodes for the current material module are added together to perform the threshold judgment again, until the sum of the authority ratio factors of all the selected approval nodes is greater than or equal to F0, then all the approval nodes that need to be selected for the current material module are determined to be jointly approved, and all the selected approval nodes are used as the approval node selection results of the current material module, and the approval effectiveness evaluation values of all the selected approval nodes for the current material module are recorded;
[0091] In the specific implementation, the persuasiveness and credibility of different approval nodes for approving the same material module are inconsistent. By calculating the authority distance between each material module and each approval node, the authority distance is converted into an authority proportional factor according to the formula to reflect the approval adaptability between each material module and each approval node. Then, according to the approval effectiveness evaluation value when each material module selects the approval node, the node with the greatest approval effectiveness is selected as the approval node selection result to ensure the overall scientific nature of the approval node selection process. At the same time, a threshold of the authority proportional factor is set to ensure that the sum of the authority proportional factors of the selected approval nodes is greater than the threshold, indicating that the approval result given by the selected single approval node or approval node combination has sufficient persuasiveness and credibility.
[0092] Calculate the comprehensive approval effectiveness evaluation value of all material modules in the current approval material according to the formula:
[0093]
[0094] Among them, E doc is the comprehensive approval effectiveness evaluation value of all material modules in the current approval material, j is the material module number of the current approval material, M doc The number of material modules divided for the current approval material, E j is the approval effectiveness evaluation value of material module j in the current approval material, n j is the number of nodes in the result of selecting the approval node of material module j in the current approval material; if material module j is determined to be jointly approved, then E j The value is the sum of the approval effectiveness evaluation values of all selected approval nodes for the current material module.
[0095] Step S600 includes the following contents:
[0096] Set the evaluation cycle of the approval node, obtain the authority ratio factor of all material modules approved by each approval node within the cycle and the current approval node; for any approval node n, calculate the comprehensive approval efficiency within the evaluation cycle according to the formula:
[0097]
[0098] Among them, E n is the comprehensive approval efficiency of approval node n in the evaluation cycle, k is the material module number of approval node n in the evaluation cycle, M n is the number of material modules approved by approval node n within the evaluation cycle, T k is the time taken for approval of material module k, F k,n is the authority ratio factor between material module k and approval node n;
[0099] Select a specified number of approval nodes from small to large based on the comprehensive approval efficiency, and feed back the comprehensive approval efficiency of the selected approval nodes to the approval node supervisor to optimize the approval efficiency;
[0100] During the specific implementation, the approval time limit for the material modules assigned to the approval nodes is taken into consideration, and the time taken for the material module approval is introduced as a calculation parameter for the comprehensive approval efficiency of the approval nodes to promote the improvement of the approval efficiency of each approval node. Feedback reminders are also provided to the approval nodes with lower comprehensive approval efficiency rankings, and the approval system is optimized periodically to ensure the sustainability of the overall process.
[0101] like Figure 2 As shown, the present invention also provides a project effectiveness prediction system based on historical approval data, including a historical data processing module, an approval material processing unit, and an approval evaluation module;
[0102] The historical data processing module is used to divide the historical project data into material modules, construct a multidimensional feature vector through feature parameter screening and quantification, and then obtain the cluster center of each approval node through a clustering algorithm; the approval material processing unit processes the approval materials according to the approval material processing method in the historical data processing module and analyzes the approval priority of each material module, calculates the approval effectiveness evaluation value of each material module of the approval material assigned to each approval node, and then selects the approval node of each material module; the approval evaluation module is used to analyze the comprehensive approval effectiveness evaluation value of the approval materials and the comprehensive approval efficiency of each approval node within the evaluation cycle;
[0103] In the specific implementation, the material submitter divides the project materials according to the established material module division method and selects the specific type of each characteristic parameter. The system assigns and quantifies the characteristic parameters according to the selected type, selects the approval node, and analyzes the overall comprehensive approval effect of the approval materials; the regulator periodically evaluates and analyzes the approval data of the approval nodes within the cycle, and optimizes the approval efficiency of the approval nodes based on the evaluation results;
[0104] The historical data processing module includes an approval material segmentation unit, a feature parameter quantification unit, and an approval node clustering unit;
[0105] The approval material segmentation unit divides the historical approval materials into material modules according to the project type and the approval material content section; the characteristic parameter quantification unit selects the characteristic parameters of each material module, assigns values to different characteristic parameters, and converts the type parameters into numerical parameters to construct a multidimensional feature vector; the approval node clustering unit performs cluster analysis based on the multidimensional feature vectors of the material modules approved by the approval nodes to obtain the cluster center of each approval node.
[0106] The approval evaluation module includes a comprehensive approval effectiveness evaluation unit and a comprehensive approval efficiency evaluation unit;
[0107] The comprehensive approval effectiveness evaluation unit is used to calculate and analyze the comprehensive approval effectiveness evaluation value of each approval material; the comprehensive approval efficiency evaluation unit is used to calculate and analyze the comprehensive approval efficiency of each approval node within the approval node evaluation cycle, select a specified number of approval nodes from small to large, and provide feedback to remind the approval node supervisors to optimize the approval efficiency.
[0108] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.
[0109] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.
Claims
1. A project effectiveness estimation method based on historical approval data, characterized in that: The analysis steps include: Step S100: Acquire historical project approval materials, divide each historical project approval material into modules according to the content section, screen and quantify the characteristic parameters of the material modules, and construct a multi-dimensional characteristic vector of each material module; Step S200: clustering approval nodes according to the multidimensional feature vectors of each material module and the final approval node to obtain the center point of each approval node cluster; Step S300: Obtain the approval materials of the current project, use the method in step S100 to perform modular segmentation and multi-dimensional feature vector construction on the approval materials, and determine the approval priority of each material module; Step S400: Calculate and analyze the authority ratio factors of each material module of each approval node and the current project approval material; Step S500: Analyze the approval node selection results of each material module according to the authority ratio factor data and the remaining approval time of the material module to be approved at each approval node, and calculate and analyze the comprehensive approval effectiveness evaluation value of the current project approval material; Step S600: setting an evaluation cycle and calculating and analyzing the comprehensive approval efficiency of each approval node within the evaluation cycle, and performing efficiency evaluation on each approval node.
2. According to claim 1, a project effectiveness estimation method based on historical approval data is characterized in that: Step S100 includes the following contents: Obtain all approval materials in historical projects, divide the approval materials of each historical project into different material modules according to the project type and approval material content section, and filter the characteristic parameters of each material module; wherein the material module characteristic parameters refer to the parameters with distinguishing characteristics between each material module; The characteristic parameters of each material module are further quantified and assigned values, each type of type parameter is assigned a different reference value, and then a multi-dimensional feature vector is constructed according to the quantified characteristic parameters of each material module.
3. According to claim 1, a project effectiveness estimation method based on historical approval data is characterized in that: Step S200 includes the following contents: Obtain the final approval nodes of each material module of the historical project approval materials, cluster the material modules with the same approval nodes according to the corresponding multi-dimensional feature vectors, and obtain the center points of each approval node cluster; For any approval node, according to the formula: in, is the equivalent multidimensional feature vector of the center point of the current approval node cluster, i is the number of the historical project material module approved by the current approval node, N is the number of historical project material modules approved by the current approval node, is the multi-dimensional feature vector of material module i.
4. According to claim 1, a project effectiveness estimation method based on historical approval data is characterized in that: Determining the approval priority of each material module in step S300 includes the following: By analyzing the order requirements of each material module in the project approval process, the approval priority of each material module is set; among them, if material module a is earlier than material module b in the approval process, the approval priority of material module a is set higher than that of material module b; for material modules belonging to different projects, if the waiting approval time of material module a is longer than that of material module b, the approval priority of material module a is set higher than that of material module b.
5. According to claim 1, a project effectiveness estimation method based on historical approval data is characterized in that: Step S400 includes the following contents: Get the multi-dimensional feature vector of each material module in the current project approval material, calculate the authority distance between each approval node and each material module of the current project approval material, select any material module m and approval node n, according to the formula: Among them, D m,n is the authority distance between approval node n and material module m, p is the parameter number in the multidimensional feature vector of each material module, n p is the number of parameters in the multidimensional feature vector of each material module, is the parameter value of the characteristic parameter p in the multidimensional characteristic vector of material module m, is the parameter value of the characteristic parameter p in the equivalent multidimensional characteristic vector of the center point of the approval node cluster n; Further calculate the authority ratio factor between material module m and approval node n according to the formula: Among them, F m,n is the authority ratio factor between material module m and approval node n, D m,n is the authority distance between approval node n and material module m, d is the approval node number, n d is the number of approval nodes, D m,d is the authority distance between material module m and approval node d.
6. A project effectiveness estimation method based on historical approval data according to claim 1, characterized in that: Step S500 includes the following contents: Obtain the priority data of each material module, and select the approval node for each material module in descending order of priority; for material module m, calculate the approval effectiveness evaluation value of approval node n for the current material module m, according to the formula: Among them, E m,n is the evaluation value of the approval effectiveness of the approval node n on the current material module m, F m,n is the authority ratio factor between material module m and approval node n, i is the number of the material module to be approved assigned by approval node n, and n m The number of material modules to be approved assigned to approval node n, t i The remaining approval time of module i of the material to be approved at approval node n; Sort the approval effectiveness evaluation values of each approval node for material module m from large to small, and select the approval node with the largest approval effectiveness evaluation value as the approval node selection result for material module m; Set the authority ratio factor threshold F0 to make a threshold judgment on the authority ratio factor of the selected approval node for the current material module; When the authority ratio factor of the selected approval node for the current material module is greater than or equal to F0, it is determined that the current material module only needs the selected approval node for approval, and the selected approval node is used as the approval node selection result of the current material module, and the approval effectiveness evaluation value of the selected approval node for the current material module is recorded; When the authority ratio factor of the selected approval node for the current material module is less than F0, the approval node is selected for the current material module again, and the authority ratio factors of the twice selected approval nodes for the current material module are added together to perform the threshold judgment again, until the sum of the authority ratio factors of all the selected approval nodes is greater than or equal to F0, then all the approval nodes that need to be selected for the current material module are determined to be jointly approved, and all the selected approval nodes are used as the approval node selection results of the current material module, and the approval effectiveness evaluation values of all the selected approval nodes for the current material module are recorded; Calculate the comprehensive approval effectiveness evaluation value of all material modules in the current approval material according to the formula: Among them, E doc is the comprehensive approval effectiveness evaluation value of all material modules in the current approval material, j is the material module number of the current approval material, M doc The number of material modules divided for the current approval material, E j is the approval effectiveness evaluation value of material module j in the current approval material, n j is the number of nodes in the result of selecting the approval node of material module j in the current approval material; if material module j is determined to be jointly approved, then E j The value is the sum of the approval effectiveness evaluation values of all selected approval nodes for the current material module.
7. The project effectiveness estimation method based on historical approval data according to claim 1 is characterized in that: Step S600 includes the following contents: Set the evaluation cycle of the approval node, obtain the authority ratio factor of all material modules approved by each approval node within the cycle and the current approval node; for any approval node n, calculate the comprehensive approval efficiency within the evaluation cycle according to the formula: Among them, E n is the comprehensive approval efficiency of approval node n in the evaluation cycle, k is the material module number of approval node n in the evaluation cycle, M n is the number of material modules that have been approved by approval node n within the evaluation cycle, T k is the time taken for approval of material module k, F k,n is the authority ratio factor between material module k and approval node n; A specified number of approval nodes are selected from small to large based on the comprehensive approval efficiency, and the comprehensive approval efficiency of the selected approval nodes is fed back to the approval node supervisor to optimize the approval efficiency.
8. A system for estimating project effectiveness based on historical approval data using a method for estimating project effectiveness based on historical approval data as claimed in any one of claims 1 to 7, characterized in that: The system includes a historical data processing module, an approval material processing unit, and an approval evaluation module; The historical data processing module is used to divide the historical project data into material modules, construct a multidimensional feature vector through feature parameter screening and quantification, and then obtain the cluster center of each approval node through a clustering algorithm; the approval material processing unit processes the approval materials according to the approval material processing method in the historical data processing module and analyzes the approval priority of each material module, calculates the approval effectiveness evaluation value of each material module of the approval material assigned to an approval node, and then selects the approval node of each material module; the approval evaluation module is used to analyze the comprehensive approval effectiveness evaluation value of the approval materials and the comprehensive approval efficiency of each approval node within the evaluation cycle.
9. A project effectiveness prediction system based on historical approval data according to claim 8, characterized in that: The historical data processing module includes an approval material segmentation unit, a feature parameter quantification unit, and an approval node clustering unit; The approval material segmentation unit segments the historical approval materials into material modules according to the project type and the approval material content section; the characteristic parameter quantification unit selects the characteristic parameters of each material module, assigns values to different characteristic parameters, and converts the type parameters into numerical parameters to construct a multi-dimensional characteristic vector; The approval node clustering unit performs cluster analysis based on the multi-dimensional feature vectors of the material modules approved by the approval nodes to obtain the cluster centers of each approval node.
10. A project effectiveness prediction system based on historical approval data according to claim 8, characterized in that: The approval evaluation module includes a comprehensive approval effectiveness evaluation unit and a comprehensive approval efficiency evaluation unit; The comprehensive approval effectiveness evaluation unit is used to calculate and analyze the comprehensive approval effectiveness evaluation value of each approval material; the comprehensive approval efficiency evaluation unit is used to calculate and analyze the comprehensive approval efficiency of each approval node within the approval node evaluation cycle, select a specified number of approval nodes from small to large, and provide feedback to remind the approval node supervisor to optimize the approval efficiency.
Citation Information
Patent Citations
Three-dimensional-based auxiliary approval process management system and method
CN113052556A
Three-dimensional model generation and analysis system and method for approval
CN113052557A
Project approval method and device, electronic equipment and readable storage medium
CN113902418A
Abnormality detection method and device, electronic equipment and computer readable medium
CN114186626A
Examination and approval chain generation method and device, electronic equipment and storage medium
CN114202312A
